cxcscmu
cxcscmu/SkillLearnBench
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/cxcscmu/SkillLearnBench --skill run2-13f-fund-summary命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Handles reading, populating, and saving .docx files using the python-docx library. Use this skill for any tasks involving template filling or modifying Word documents.
Perform various data analysis on SEC 13-F and obtain some insights of fund activities such as number of holdings, AUM, and change of holdings between two quarters.
This skill includes search capability in 13F, such as fuzzy search a fund information using possibly inaccurate name, or fuzzy search a stock cusip info using its name.
基于 SOC 职业分类
正在显示 SKILL.md
| name | run2_13f-fund-summary |
| description | How to calculate a fund's actual AUM and total unique stock count for modern SEC 13F data. |
Starting in 2023, the SEC began requiring funds to report exact dollar amounts in the SUMMARYPAGE.tsv and INFOTABLE.tsv VALUE columns, replacing the old system where values were reported in thousands.
The total value is now precisely reported in exact dollars.
import pandas as pd
accession_number = "0001037389-25-000064"
quarter = "2025-q3"
summary = pd.read_csv(f"/root/{quarter}/SUMMARYPAGE.tsv", sep="\t", dtype=str)
match = summary[summary["ACCESSION_NUMBER"] == accession_number]
if not match.empty:
# 13F forms currently report VALUES in EXACT dollars (no longer in thousands)
aum = float(match["TABLEVALUETOTAL"].iloc[0])
print(f"Total AUM: ${aum:,.2f}")
Since one CUSIP can have multiple rows (for different investment discretion types or voting authority), use nunique() on the CUSIP column.
import pandas as pd
infotable = pd.read_csv(f"/root/2025-q3/INFOTABLE.tsv", sep="\t", dtype=str)
holdings = infotable[infotable["ACCESSION_NUMBER"] == "0001037389-25-000064"]
# Number of unique CUSIPs represents the total number of stocks held
unique_stocks = holdings["CUSIP"].nunique()
print(f"Number of Unique Stocks Held: {unique_stocks}")